metadata
license: apache-2.0
base_model: bigcode/starcoder2-3b
language:
- en
tags:
- mlx
- ffai
- quantized
- 4bit
- affine
starcoder2-3b-4bit
4-bit affine quantization of bigcode/starcoder2-3b, produced with FFAI 0.1.0's ffai convert (mlx-affine format, group_size=64).
Conversion
ffai convert bigcode/starcoder2-3b --bits 4 \
--upload-repo ekryski/starcoder2-3b-4bit
See also
- FFAI — fast Apple Silicon LLM inference.
Model.load("ekryski/starcoder2-3b-4bit")runs this checkpoint end-to-end. - FFAI quickstart
- FFAI quantization docs